News for hackers. Stuff that matters.

A comment on Mastering Chess and Shogi by Self-Play with General Reinforcement Learning. Parent comment

Re:Mastering Chess and Shogi by Self-Play with General Reinf... by allenz on Wednesday December 06, 2017 @02:18AM (#15859199)
> which would never be considered by ... a superhuman

How would you know?

[ Parent | on HN ]
Re:Mastering Chess and Shogi by Self-Play with General Reinf... by thom on Wednesday December 06, 2017 @02:23AM (#15859217)
I don’t see it in my database, and it’s never been played on Lichess, even in bullet games.
[ Parent | on HN ]
Re:Mastering Chess and Shogi by Self-Play with General Reinf... by allenz on Wednesday December 06, 2017 @03:15AM (#15859467)
Which, of course, is not evidence that a superhuman wouldn't consider such a move. AlphaGo also made unusual moves that looked like mistakes, but turned out to be insights.
[ Parent | on HN ]
Re:Mastering Chess and Shogi by Self-Play with General Reinf... by thom on Wednesday December 06, 2017 @03:17AM (#15859477)
Apologies, misread the parent comment!
[ Parent | on HN ]
Re:Mastering Chess and Shogi by Self-Play with General Reinf... by zwischenzug on Wednesday December 06, 2017 @02:20AM (#15859209)
Ask any GM.
[ Parent | on HN ]
Re:Mastering Chess and Shogi by Self-Play with General Reinf... by gamegoblin on Wednesday December 06, 2017 @03:08AM (#15859430)
How would a GM (human) know what would be played by a superhuman?
[ Parent | on HN ]